Hugging Face's logo
Michael Han's picture
210 21 228

Michael Han

shimmyshimmer
iammano's profile picture ahmeterdempmk's profile picture DaCruzSilva-1979's profile picture
·
https://unsloth.ai

AI & ML interests

None yet

Recent Activity

upvoted a collection 24 minutes ago
Llama 4
new activity about 2 hours ago
unsloth/Llama-4-Scout-17B-16E-Instruct-unsloth-bnb-4bit:Model issue with 64GB ram
liked a model about 2 hours ago
unsloth/Llama-4-Scout-17B-16E-Instruct-unsloth-bnb-4bit
View all activity

Organizations

Unsloth AI's profile picture Hugging Face Discord Community's profile picture

shimmyshimmer's activity

New activity in unsloth/Llama-4-Scout-17B-16E-Instruct-unsloth-bnb-4bit about 2 hours ago

Model issue with 64GB ram

2
#4 opened about 16 hours ago by
llama-anon
New activity in unsloth/gemma-3-27b-it-GGUF about 14 hours ago

Does not support multimodal input

1
#5 opened 2 days ago by
RamboRogers
New activity in unsloth/Llama-4-Scout-17B-16E-Instruct-unsloth-bnb-4bit about 17 hours ago

This looks like the base and not bnb-4bit?

4
#2 opened 1 day ago by
bjj

ValueError: Unrecognized image processor in unsloth/Llama-4-Scout-17B-16E-Instruct-unsloth-bnb-4bit. Should have a `image_processor_type` key

1
#3 opened about 20 hours ago by
ievnsk
New activity in unsloth/Llama-4-Scout-17B-16E-Instruct-unsloth-bnb-4bit 1 day ago

What's up with the minimal decrease in file size from fp16?

1
#1 opened 1 day ago by
jth01
New activity in unsloth/gemma-3-4b-it-unsloth-bnb-4bit 5 days ago

Does not work at all

3
#1 opened 13 days ago by
zokica
New activity in unsloth/Qwen2.5-VL-32B-Instruct-unsloth-bnb-4bit 5 days ago

VRAM requirements?

2
#3 opened 5 days ago by
hamaadtahiir
New activity in unsloth/DeepSeek-V3-0324-GGUF 5 days ago

Running Model "unsloth/DeepSeek-V3-0324-GGUF" with vLLM does not working

2
#11 opened 6 days ago by
puppadas
New activity in unsloth/gemma-3-4b-it 6 days ago

Update README.md

1
#2 opened 7 days ago by
seniichev
New activity in unsloth/DeepSeek-V3-0324-GGUF 7 days ago

671B params or 685B params?

6
#8 opened 8 days ago by
createthis

The UD-IQ2_XXS is surprisingly good, but it's good to know that it degrades gradually but significantly after about 1000 tokens.

1
#9 opened 7 days ago by
mmbela

quantize.* missing

2
#10 opened 7 days ago by
phymbert
New activity in unsloth/Mistral-Small-3.1-24B-Instruct-2503-GGUF 9 days ago

Can`t see the image in LM studio.

4
#1 opened 14 days ago by
Technobiotik
New activity in unsloth/DeepSeek-V3-0324-GGUF 9 days ago

Any plan for IQS_XS or IQS_XXS ?

1
#6 opened 9 days ago by
bobchenyx
New activity in unsloth/DeepSeek-V3-0324-GGUF 10 days ago

Added IQ1_S version to Ollama

3
#4 opened 12 days ago by
Muhammadreza
New activity in unsloth/DeepSeek-V3-0324-GGUF 12 days ago

Is the 2.51bit model using imatrix?

7
#3 opened 12 days ago by
daweiba12

Will you release the imatrix.dat used for the quants?

2
#2 opened 12 days ago by
tdh111

Would There be Dynamic Qunatized Versions like 2.51bit

8
#1 opened 13 days ago by
MotorBottle
New activity in unsloth/gemma-3-12b-it-unsloth-bnb-4bit 16 days ago

Error loading model with vllm

1
#1 opened 18 days ago by
ggeo
New activity in unsloth/gemma-3-27b-it-GGUF 18 days ago

Cannot input image in ollama for gemma-3-27b-it-GGUF:Q4_K_M

9
#3 opened 20 days ago by
kitc